Abstract
In this paper, we propose a novel approach to commodity classification from surveillance videos by utilizing logo data on trucks. Broadly, most logos can be classified as predominantly text or predominantly images. For the former, we leverage state-of-the-art deep-learning-based text recognition algorithms on images. For the latter, we develop a two-stage image retrieval algorithm consisting of a universal logo detection stage that outputs all potential logo positions, followed by a logo recognition stage designed to incorporate advanced image representations. We develop an integrated approach to combine predictions from both the text-based and image-based solutions, which can help determine the commodity type that is potentially being hauled by trucks. We evaluated these models on videos collected in collaboration with the state transportation entity and achieved promising performance. This, along with prior work on trailer classification, can be effectively used for automatically deriving commodity types for trucks moving on highways.
Highlights
For text-based logos, we employ state-of-the-art solutions for text detection [25,26] and recognition [27,28] to obtain raw text predictions with high accuracy. These predicted logo texts were matched to our built commodity database by comparing these texts with recorded company names via simple string matching algorithms; To identify image-based logos that do not contain text information, we developed a novel two-stage image-based approach: a universal logo detection stage that outputs all potential logo positions within images, followed by a logo recognition stage designed to incorporate various advanced image representations
The reverse image search is a content-based image retrieval (CBIR) query approach [36] in which we provide the system with a sample image to search for related concepts about this image
We evaluated our logo detection and recognition approaches on video frames captured by roadside cameras provided by the Florida Department of Transportation (FDOT)
Summary
125 million households, nearly 7.7 million business establishments, and 90,000 governmental units in the U.S require efficient and reliable movement of freight [1]. Freight transportation has become an indicator of economic growth and regional development, which makes freight analysis an increasingly important area. The main objective of freight analysis is to reduce freight transit time and transportation cost and improve the reliability of freight movement. It is beneficial in mitigating traffic congestion, better planning land use, and improving economic competitiveness [2]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
